NDLI: Derandomizing Stochastic Prediction Strategies

Please wait, while we are loading the content...

Machine Learning : Volume 106

Machine Learning : Volume 105

Machine Learning : Volume 104

Machine Learning : Volume 103

Machine Learning : Volume 102

Machine Learning : Volume 101

Machine Learning : Volume 100

Machine Learning : Volume 99

Machine Learning : Volume 98

Machine Learning : Volume 97

Machine Learning : Volume 96

Machine Learning : Volume 95

Machine Learning : Volume 94

Machine Learning : Volume 93

Machine Learning : Volume 92

Machine Learning : Volume 91

Machine Learning : Volume 90

Machine Learning : Volume 89

Machine Learning : Volume 88

Machine Learning : Volume 87

Machine Learning : Volume 86

Machine Learning : Volume 85

Machine Learning : Volume 84

Machine Learning : Volume 83

Machine Learning : Volume 82

Machine Learning : Volume 81

Machine Learning : Volume 80

Machine Learning : Volume 79

Machine Learning : Volume 78

Machine Learning : Volume 77

Machine Learning : Volume 76

Machine Learning : Volume 75

Machine Learning : Volume 74

Machine Learning : Volume 73

Machine Learning : Volume 72

Machine Learning : Volume 71

Machine Learning : Volume 70

Machine Learning : Volume 69

Machine Learning : Volume 68

Machine Learning : Volume 67

Machine Learning : Volume 66

Machine Learning : Volume 65

Machine Learning : Volume 64

Machine Learning : Volume 63

Machine Learning : Volume 62

Machine Learning : Volume 61

Machine Learning : Volume 60

Machine Learning : Volume 59

Machine Learning : Volume 58

Machine Learning : Volume 57

Machine Learning : Volume 56

Machine Learning : Volume 55

Machine Learning : Volume 54

Machine Learning : Volume 53

Machine Learning : Volume 52

Machine Learning : Volume 51

Machine Learning : Volume 50

Machine Learning : Volume 49

Machine Learning : Volume 48

Machine Learning : Volume 47

Machine Learning : Volume 46

Machine Learning : Volume 45

Machine Learning : Volume 44

Machine Learning : Volume 43

Machine Learning : Volume 42

Machine Learning : Volume 41

Machine Learning : Volume 40

Machine Learning : Volume 39

Machine Learning : Volume 38

Machine Learning : Volume 37

Machine Learning : Volume 36

Machine Learning : Volume 35

Machine Learning : Volume 35, Issue 3, June 1999

Introducing the Special Issue of Machine Learning Selected from Papers Presented at the 1997 Conference on Computational Learning Theory, COLT '97

Universal Portfolios With and Without Transaction Costs

A Dichotomy Theorem for Learning Quantified Boolean Formulas

Estimation of Time-Varying Parameters in Statistical Models: An Optimization Approach

Derandomizing Stochastic Prediction Strategies

Machine Learning : Volume 35, Issue 2, May 1999

Machine Learning : Volume 35, Issue 1, April 1999

Machine Learning : Volume 34

Machine Learning : Volume 33

Machine Learning : Volume 32

Machine Learning : Volume 31

Machine Learning : Volume 30

Machine Learning : Volume 29

Machine Learning : Volume 28

Machine Learning : Volume 27

Machine Learning : Volume 26

Derandomizing Stochastic Prediction Strategies

Content Provider	Springer Nature Link
Author	Vovk, V.
Copyright Year	1999
Abstract	In this paper we continue study of the games of prediction with expert advice with uncountably many experts. A convenient interpretation of such games is to construe the pool of experts as one “stochastic predictor”, who chooses one of the experts in the pool at random according to the prior distribution on the experts and then replicates the (deterministic ) predictions of the chosen expert. We notice that if the stochastic predictor's total loss is at most L with probability at least p then the learner's loss can be bounded by cL + aln $$\frac{1}{{\text{P}}}$$ for the usual constants c and a. This interpretation is used to revamp known results and obtain new results on tracking the best expert. It is also applied to merging overconfident experts and to fitting polynomials to data.
Starting Page	247
Ending Page	282
Page Count	36
File Format	PDF
ISSN	08856125
Journal	Machine Learning
Volume Number	35
Issue Number	3
e-ISSN	15730565
Language	English
Publisher	Kluwer Academic Publishers
Publisher Date	1999-01-01
Publisher Place	Boston
Access Restriction	One Nation One Subscription (ONOS)
Subject Keyword	Computer Science Artificial Intelligence (incl. Robotics) Automation and Robotics
Content Type	Text
Resource Type	Article
Subject	Artificial Intelligence Software

Central Library (ISO-9001:2015 Certified)
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal, India | PIN - 721302

See location in the Map
03222 282435
Mail: support@ndl.gov.in

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in